조성현 / csh-parser

Go to a project
Toggle navigation Toggle navigation pinning
조성현
8f14a245 0 parents

init

Inline Side-by-side
Showing 4 changed files with 317 additions and 0 deletions

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 14
VisualStudioVersion = 14.0.25420.1
MinimumVisualStudioVersion = 10.0.40219.1
Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "dblpJsonParser", "dblpJsonParser\dblpJsonParser.vcxproj", "{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|x64 = Debug|x64
Debug|x86 = Debug|x86
Release|x64 = Release|x64
Release|x86 = Release|x86
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Debug|x64.ActiveCfg = Debug|x64
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Debug|x64.Build.0 = Debug|x64
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Debug|x86.ActiveCfg = Debug|Win32
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Debug|x86.Build.0 = Debug|Win32
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Release|x64.ActiveCfg = Release|x64
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Release|x64.Build.0 = Release|x64
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Release|x86.ActiveCfg = Release|Win32
{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}.Release|x86.Build.0 = Release|Win32
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
EndGlobal
<?xml version="1.0" encoding="utf-8"?>
<Project DefaultTargets="Build" ToolsVersion="14.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup Label="ProjectConfigurations">
<ProjectConfiguration Include="Debug|Win32">
<Configuration>Debug</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|Win32">
<Configuration>Release</Configuration>
<Platform>Win32</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Debug|x64">
<Configuration>Debug</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
<ProjectConfiguration Include="Release|x64">
<Configuration>Release</Configuration>
<Platform>x64</Platform>
</ProjectConfiguration>
</ItemGroup>
<PropertyGroup Label="Globals">
<ProjectGuid>{D0FA588C-B5C0-422F-8CA1-4FD40054BD1C}</ProjectGuid>
<Keyword>Win32Proj</Keyword>
<RootNamespace>dblpJsonParser</RootNamespace>
<WindowsTargetPlatformVersion>8.1</WindowsTargetPlatformVersion>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<PlatformToolset>v140</PlatformToolset>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<PlatformToolset>v140</PlatformToolset>
<WholeProgramOptimization>true</WholeProgramOptimization>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>true</UseDebugLibraries>
<PlatformToolset>v140</PlatformToolset>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
<ConfigurationType>Application</ConfigurationType>
<UseDebugLibraries>false</UseDebugLibraries>
<PlatformToolset>v140</PlatformToolset>
<WholeProgramOptimization>true</WholeProgramOptimization>
<CharacterSet>Unicode</CharacterSet>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
<ImportGroup Label="ExtensionSettings">
</ImportGroup>
<ImportGroup Label="Shared">
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
</ImportGroup>
<PropertyGroup Label="UserMacros" />
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<LinkIncremental>true</LinkIncremental>
<IncludePath>C:\boost\boost_1_62_0;C:\JsonCpp\jsoncpp-master\include;$(IncludePath)</IncludePath>
<LibraryPath>C:\boost\boost_1_62_0\stage\lib;C:\JsonCpp\jsoncpp-master\build\vs71\debug\lib_json;$(LibraryPath)</LibraryPath>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<LinkIncremental>true</LinkIncremental>
<IncludePath>C:\boost\boost_1_62_0;C:\JsonCpp\jsoncpp-master\include;$(IncludePath)</IncludePath>
<LibraryPath>C:\boost\boost_1_62_0\stage\lib;C:\JsonCpp\jsoncpp-master\build\vs71\debug\lib_json;$(LibraryPath)</LibraryPath>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
<ClCompile>
<PrecompiledHeader>
</PrecompiledHeader>
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>WIN32;_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<SDLCheck>true</SDLCheck>
<AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalLibraryDirectories>%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
<AdditionalDependencies>json_vc71_libmtd.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
<ClCompile>
<PrecompiledHeader>
</PrecompiledHeader>
<WarningLevel>Level3</WarningLevel>
<Optimization>Disabled</Optimization>
<PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<SDLCheck>true</SDLCheck>
<AdditionalIncludeDirectories>%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<GenerateDebugInformation>true</GenerateDebugInformation>
<AdditionalLibraryDirectories>%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
<AdditionalDependencies>json_vc71_libmtd.lib;%(AdditionalDependencies)</AdditionalDependencies>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PrecompiledHeader>
</PrecompiledHeader>
<Optimization>MaxSpeed</Optimization>
<FunctionLevelLinking>true</FunctionLevelLinking>
<IntrinsicFunctions>true</IntrinsicFunctions>
<PreprocessorDefinitions>WIN32;NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<SDLCheck>true</SDLCheck>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
<OptimizeReferences>true</OptimizeReferences>
<GenerateDebugInformation>true</GenerateDebugInformation>
</Link>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
<ClCompile>
<WarningLevel>Level3</WarningLevel>
<PrecompiledHeader>
</PrecompiledHeader>
<Optimization>MaxSpeed</Optimization>
<FunctionLevelLinking>true</FunctionLevelLinking>
<IntrinsicFunctions>true</IntrinsicFunctions>
<PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
<SDLCheck>true</SDLCheck>
</ClCompile>
<Link>
<SubSystem>Console</SubSystem>
<EnableCOMDATFolding>true</EnableCOMDATFolding>
<OptimizeReferences>true</OptimizeReferences>
<GenerateDebugInformation>true</GenerateDebugInformation>
</Link>
</ItemDefinitionGroup>
<ItemGroup>
<ClCompile Include="main.cpp" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
<ImportGroup Label="ExtensionTargets">
</ImportGroup>
</Project>
\ No newline at end of file
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup>
<Filter Include="소스 파일">
<UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D752A2FF}</UniqueIdentifier>
<Extensions>cpp;c;cc;cxx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
</Filter>
<Filter Include="헤더 파일">
<UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
<Extensions>h;hh;hpp;hxx;hm;inl;inc;xsd</Extensions>
</Filter>
<Filter Include="리소스 파일">
<UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
<Extensions>rc;ico;cur;bmp;dlg;rc2;rct;bin;rgs;gif;jpg;jpeg;jpe;resx;tiff;tif;png;wav;mfcribbon-ms</Extensions>
</Filter>
</ItemGroup>
<ItemGroup>
<ClCompile Include="main.cpp">
<Filter>소스 파일</Filter>
</ClCompile>
</ItemGroup>
</Project>
\ No newline at end of file
#include <cstdio>
#include <exception>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>
#include <boost/regex.hpp>
#include <json/json.h>
using namespace std;
const char* DBLP_FILENAME = "test.json";
const char* DBLP_COAUTHOR_FILENAME = "tmp_dblp_coauthorship.json";
const string COLUMN_DELIMITER = "||";
const string AUTHOR_DELIMITER = "&&";
int main() {
//init
Json::Value root;
Json::Reader reader;
ifstream dblp_paper, dblp_coauthor;
ofstream dblp_paper_out, dblp_coauthor_out;
try {
//1. dblp paper dataset
dblp_paper.open(DBLP_FILENAME);
dblp_paper_out.open((string(DBLP_FILENAME)+string(".out")).c_str());
if (!dblp_paper || !dblp_paper_out) {
throw exception("dblp paper file error");
}
printf("* complete open\n");
if (!reader.parse(dblp_paper, root)) {
throw exception("parse error");
}
printf("* complete parse\n");
Json::Value row;
Json::Value coauthors;
std::string paper_key;
std::vector<string> coauthor_list;
int year;
int count = 1;
for (auto it=root.begin();
it!=root.end();
++it) {
//Àüó¸®
row.clear();
coauthors.clear();
coauthor_list.clear();
//print
if (count%1000000 == 0) {
printf("* [%d]\n", count);
}
//row ´ÜÀ§·Î read
row = *it;
paper_key = row[0].asString();
coauthors = row[1];
for (auto coit=coauthors.begin(); coit!=coauthors.end(); ++coit) {
coauthor_list.push_back(coit->asString());
}
year = ((row[2].isNull())?-1:row[2].asInt());
//write
dblp_paper_out << paper_key << COLUMN_DELIMITER;
for (auto auit=coauthor_list.begin(); auit!=coauthor_list.end(); ++auit) {
dblp_paper_out << (*auit);
if () {
dblp_paper_out << AUTHOR_DELIMITER;
}
}
dblp_paper_out << endl;
//ÈÄó¸®
++count;
}
printf("* complete convert dblp paper\n");
//2. dblp coauthorship dataset
//dblp_coauthor.open(DBLP_COAUTHOR_FILENAME);
}
catch (const exception& e) {
cerr << "Error: " << e.what() << endl;
return -1;
}
//release
dblp_paper.close();
dblp_coauthor.close();
dblp_paper_out.close();
dblp_coauthor_out.close();
return 0;
}
\ No newline at end of file